activity
20242026
most citedResolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs

1 citations · 1 across the 4 of their papers we have counts for

collaborators

10 papers

cs.CL2026

Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs

Hongliang Liu, Tung-Ling Li, Yuhao Wu

Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backpropagation, followed by a on…

cs.CL2026

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Junjie Li, Xinrui Guo, Yuhao Wu +3

What happens when a storyteller forgets its own story? Large Language Models (LLMs) can now generate narratives spanning tens of thousands of words, but they often fail to maintain…

cs.CV2026

From Perception to Action: An Interactive Benchmark for Vision Reasoning

Yuhao Wu, Maojia Song, Yihuai Lan +8

Understanding the physical structure is essential for real-world applications such as embodied agents, interactive design, and long-horizon manipulation. Yet, prevailing Vision-Lan…

cs.CL2025

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

Yuhao Wu, Yushi Bai, Zhiqiang Hu +2

Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text…

cs.CL2025

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

Yuhao Wu, Yushi Bai, Zhiqiang Hu +2

Ultra-long generation by large language models (LLMs) is a widely demanded scenario, yet it remains a significant challenge due to their maximum generation length limit and overall…

cs.CL20251 cited

Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs

Ziyu Ge, Yuhao Wu, Daniel Wai Kit Chin +2

Large Language Models (LLMs) augmented with retrieval mechanisms have demonstrated significant potential in fact-checking tasks by integrating external knowledge. However, their re…